Fig. 2

A–B Classification performance (AUPR) on the test set of the somatic cells (A) and leukocytes datasets (B). C–D Computational time required for each method to produce a signature including cross-validation and testing for the somatic cells (C) and leukocytes (D) datasets. E Mean ranks of the methods across all datasets based on the AUPR. The best method, Elastic Net, and its 95% confidence interval (Friedman and Nemenyi post hoc test) is highlighted in gray. Methods that do not overlap at all with the highlighted area, are significantly worse than the highlighted methods